ClawHub
Back to skill

Security audit

GuanXing 观星

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed fortune/metaphysics API skill that sends user-provided personal details to GuanXing, with no evidence of hidden code, persistence, or unrelated access.

Install only if you are comfortable sending names, birth dates, birth hours, dream descriptions, compatibility details, crypto token symbols, and personal questions to heartai.zeabur.app. Keep GUANXING_API_KEY private and ask the agent to confirm before sending especially sensitive details.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The README encourages users to submit highly sensitive personal data such as birth date/time, dreams, relationship details, and other spiritual or profiling inputs to an external API, but it provides no privacy notice, data handling summary, retention policy, or consent warning. Because this skill's core use cases inherently involve personal and potentially sensitive data, the lack of disclosure materially increases privacy and compliance risk.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill explicitly allows autonomous invocation on broad prompts such as 'fortune', 'zodiac', 'Feng Shui', and related topics, which are common in ordinary conversation. This can cause the agent to send user data to an external service without sufficiently explicit user intent at the moment of transmission, increasing the risk of surprise data disclosure.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.